Open AccessRemining Useful Life Prediction of Equipment Driven by Multi-Sensor Data
Author(s) -
Hui-yong Zeng,
Lin Deng,
Jun Guo,
Jian Wang,
Tengjiao Wang,
Tao Gu
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1213/5/052005
Subject(s) - wiener process , particle filter , reliability engineering , computer science , degradation (telecommunications) , process (computing) , maximum likelihood , engineering , statistics , filter (signal processing) , mathematics , electronic engineering , computer vision , operating system
This paper presents a method for predicting the remining useful life (RUL) of equipment by using multi-sensor monitoring data of equipment. Firstly, the performance degradation of equipment is evaluated based on the maximum information coefficient. Then the performance degradation model is built by using Wiener process with non-linear drift. The maximum likelihood is used to estimate the parameters of the model, and the probability density distribution of RUL considering random failure threshold is deduced. Finally, the parameters of the model are updated by improved particle filter, and the RUL of the remaining equipment is predicted.